NVIDIA Nemotron™ 3 Super Meetup

🌟 Join Us for NVIDIA Nemotron 3 Super Meetup 🌟

Fill out this form: https://forms.gle/tPGZAuXupYGsSgMD7

This interactive workshop dives deep into NVIDIA Nemotron 3 Super, NVIDIA’s newly released 120B (12B active-parameter) open hybrid Mamba-Transformer Mixture-of-Experts (MoE) model. Designed to solve complex, dense technical problems autonomously, NVIDIA Nemotron 3 Super handles long-context analysis, precise reasoning, and coding while remaining computationally efficient.

Throughout this workshop, participants will explore the model's architectural innovations—such as Latent MoE, Multi-Token Prediction (MTP), and its hybrid backbone—and learn how to customize, optimize, and deploy it using NVIDIA's fully open weights, datasets, and recipes.

Prerequisites

• Languages/tools—Python
• Frameworks— PyTorch, TensorRT-LLM, Triton Inference Server, SGLang, vLLM.
• Sign-up with build.nvidia.com and create your account
• Bring your Laptop to this Workshop

Laptop with internet access - Ideal minimum: 5 Mbps download / 1–2 Mbps upload. This will ensure consistent access to the lab. This will ensure consistent access to the lab.

Instructor: Megh Makwana - Manager, Applied Gen AI Solution Engineering, NVIDIA

Megh’s work converges on building foundational AI models, scaling GPU workloads efficiently, and supporting CSPs in developing AI platforms with NVIDIA AI Enterprise.

Agenda:

• 09:00 AM - 09:30 AM: NVIDIA Nemotron Strategy: Open Datasets, Weights, Frameworks and Recipes.
• 09:30 AM - 10:00 AM: Deep-Dive into NVIDIA Nemotron-3 Super Architecture Design
• 10:30 AM - 11:15 AM: Efficient Serving & Deployment of Nemotron Model using vLLM, SGLang and TensorRT-LLM Cookbooks
• 11:15 AM - 12:30 PM: Building Agentic Workflow using Nemotron models
• 12:30 PM- 1:00 PM : Use case/Demo by Sarvam AI

Show-n-Tell: Community Demos

Local builders, researchers, and practitioners will share what they've been building with NVIDIA Nemotron from RAG pipelines to agents to domain-specific fine-tunes. Short, sharp, and hands-on.

Time: 1:00 PM - 2:00 PM - Lunch
Time: 2:00 PM - 2:30 PM - Speaker, Amadeus
Time: 2:30 PM - 3:00 PM - Get Started with NemoClaw using Docker Labspaces by Ajeet Singh Raina, DevRel Docker
Time: 3:00 PM - 3:30 PM - Manjunath Janardhan, AI/ML Computational Science Sr. Manager, Accenture
3:30 PM onwards - Networking & Wrap-Up

📢 Register Now! Don't miss out—sign up today by filling out the form. https://forms.gle/tPGZAuXupYGsSgMD7